© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 21-LLAMASCOPE-RES-32K
    11. 12769
    Prev
    Next
    INDEX
    Explanations

    characters engaged in suspicious or deceitful behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themselves
    -0.32
     yourselves
    -0.26
     Ñģами
    -0.22
     должно
    -0.20
     nhau
    -0.19
     hät
    -0.18
    Their
    -0.17
     Their
    -0.17
     Ñģказала
    -0.17
    ä¸Ī夫
    -0.17
    POSITIVE LOGITS
     himself
    0.96
     his
    0.62
     Himself
    0.57
    his
    0.52
    ä»ĸçļĦ
    0.40
     ÙĨÙģسÙĩ
    0.40
     seinem
    0.38
     zijn
    0.38
    ï¼Įä»ĸ
    0.37
    ãĢĤä»ĸ
    0.35
    Activations Density 3.257%

    No Known Activations